arxiv:2606.14885
ZhuofengLi
ZhuofengLi
AI & ML interests
Agents, Reasoning LLMs/VLLMs, RL
Recent Activity
updated a dataset 10 days ago
ZhuofengLi/Harbor-SWE-Trajectory published a dataset 11 days ago
ZhuofengLi/Harbor-SWE-Trajectory authored a paper about 1 month ago
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its MechanismOrganizations
models 38
ZhuofengLi/Qwen3-4B-hardtests-frontier-full
196k • Updated • 17
ZhuofengLi/Qwen3-4B-hardtests-frontier-filtered-full
196k • Updated • 17
ZhuofengLi/Qwen3.5-27B-hardtests-sft-synthetic-merged
27B • Updated • 7
ZhuofengLi/Qwen3.5-27B-hardtests-sft-synthetic-lora
Updated
ZhuofengLi/hardtests-sft-qwen3.5-27b-checkpoint-180
27B • Updated • 3
ZhuofengLi/hardtests-sft-qwen3.5-27b-r16-epoch2
Updated • 6
ZhuofengLi/hardtests-sft-qwen3.5-27b-r16-epoch1
Updated • 4
ZhuofengLi/hardtests-sft-qwen3.5-27b-epoch1
Updated • 4
ZhuofengLi/qwen3.5-9b-nemotron-sft-ckpt300
1.47M • Updated • 4
ZhuofengLi/qwen3.5-9b-nemotron-sft-ckpt250
1.47M • Updated • 4
datasets 35
ZhuofengLi/Harbor-SWE-Trajectory
Updated • 88
ZhuofengLi/pretraining-pretokenized-smollm3
Viewer • Updated • 192 • 149
ZhuofengLi/hardtests-sft-qwen3.5-27b
Viewer • Updated • 11.3k • 54
ZhuofengLi/hardtests-sft-qwen3.5-27b-synthetic
Viewer • Updated • 9.07k • 24
ZhuofengLi/megatron-configs
Updated • 227
ZhuofengLi/fineweb-edu-pretokenized-10b
Viewer • Updated • 42 • 108
ZhuofengLi/fineweb-edu-pretokenized-llama3-100b
Viewer • Updated • 140 • 269
ZhuofengLi/Qwen3.5-27B-hardtests-sft-merged
Updated • 7
ZhuofengLi/bcp-eval-logs
Viewer • Updated • 238 • 3
ZhuofengLi/bcplus-eval-100
Viewer • Updated • 1.53k • 16